R Notebook

library(ggplot2)

package ‘ggplot2’ was built under R version 3.6.2

library(CodeClanData)

Attaching package: ‘CodeClanData’

The following object is masked from ‘package:datasets’:

    volcano

library(tidyverse)

Registered S3 methods overwritten by 'dbplyr':
  method         from
  print.tbl_lazy     
  print.tbl_sql      
── Attaching packages ───────────────────────────────────────────────────── tidyverse 1.3.0 ──
✓ tibble  3.0.3     ✓ dplyr   1.0.0
✓ tidyr   1.1.0     ✓ stringr 1.4.0
✓ readr   1.3.1     ✓ forcats 0.5.0
✓ purrr   0.3.4     
package ‘tibble’ was built under R version 3.6.2package ‘tidyr’ was built under R version 3.6.2package ‘purrr’ was built under R version 3.6.2package ‘dplyr’ was built under R version 3.6.2── Conflicts ──────────────────────────────────────────────────────── tidyverse_conflicts() ──
x dplyr::filter() masks stats::filter()
x dplyr::lag()    masks stats::lag()

library(ggthemes)
library(viridis)

Loading required package: viridisLite

COMPARISON

Create a suitable plot for the following three datasets:

late_deliveries

Late Deliveries

ggplot(late_deliveries) +
 aes(x = date, y = late_deliveries, fill = late_deliveries, bins = 20) +
  geom_col(position = "dodge") +
  scale_fill_distiller(palette = "Pastel2") +
  theme_bw() + 
  labs(
    x = "Date",
    y = "late deliveries",
    title = "Late Deliveries"
  ) +  
  theme(title = element_text(size = 16, face = "italic", colour = "Blue"))

solution 2

ggplot(late_deliveries) +
  aes(x = date, y = late_deliveries) +
  geom_line() + 
  geom_point() + 
  labs(x = "year", y = "number of late deliveries") + 
  theme_minimal()

Recovery time

recovery_times

ggplot(recovery_times) +
  aes(x = recovery, y = prognosis, fill = treatment_group) + 
  geom_col(position = "dodge") +
  scale_fill_hue(h = c(120,300), c = 40, l = 45) +
  theme_classic(11) +
  labs(
    x = "Recovery",
    y = "Prognosis",
    title = "Recovery Times"
  ) +
  theme(
    title = element_text(size = 15, face = "bold", colour = "blue"),
    panel.background = element_rect(fill = "Pink"), 
    panel.grid = element_blank(),
    plot.title = element_text(size = 15, face = "bold", colour = "blue")
  )

NA
NA

solution 2

ggplot(recovery_times) +
  aes(x = treatment_group, y = recovery, fill = prognosis) +
  geom_col(position = "dodge") + 
  labs(x = "\n Treatment Group", y = "Recovery time (months) \n") + 
    scale_fill_colorblind()

NA
NA

Fitness Level

fitness_levels

ggplot(fitness_levels) + 
  aes(x = age, y = fitness_score, colour = group) +
  geom_line() +
  theme_light() + 
  facet_wrap(~ group, ncol = 10, scales = "free") +
  scale_color_gradient2_tableau()

NA
NA

Solution 2

ggplot(fitness_levels) +
  aes(x = age, y = fitness_score, group = child, color = child) +
  geom_line() +
  geom_point() +
  facet_wrap(~ group, ncol = 5) + 
  labs(y = "fitness score \n", x = "\n age (years)", title = "Individual child fitness score by Group") + 
  scale_colour_hue(guide = guide_legend(nrow = 10, byrow = TRUE))

CONNECTION

Blood Pressure

ggplot(blood_pressure) +
  aes(x = systolic_blood_pressure_mm_hg, y = daily_saturated_fat_intake_mg, colour = daily_saturated_fat_intake_mg) +
  geom_point() +
  scale_colour_gradient2(low = "blue", high = "red", mid = "white", midpoint = 15) +
  labs(
    x = "Sys Blood Pre",
    y = "Daily fat intake (mg)",
    title = "Blood Pressue",
    subtitle = "fat Intake (mg)"
  ) + 
  theme_light()

Solution 2

ggplot(blood_pressure) +
  aes(
    x = daily_saturated_fat_intake_mg,
    y = systolic_blood_pressure_mm_hg
  ) +
  geom_point() + 
  labs(x = "daily fat intake (mg)", y = "systolic blood pressure (mmHg)")

Car use

car_use

ggplot(car_use) +
  aes(x = city, y = population, colour = car_use_percent) +
  geom_point() +
  scale_color_distiller(palette = "PuOr") +
  theme_dark() +
  labs(
    title = "Car Use", 
    subtitle = "Car use"
  )

NA
NA
NA

solution 2

ggplot(car_use) +
  aes(
    x = car_use_percent,
    y = air_so2_concentration_ppm,
    size = population
  ) +
  geom_point(alpha = 0.5) + 
  labs(x = "car use (%)", y = "air CO2 concentration (ppm)")

DISTRIBUTION

D20 Outcome

ggplot(d20_outcomes) +
  aes(x = outcome) +
  geom_histogram(bins = 20, col = "white") 

solution 2

ggplot(d20_outcomes) +
  aes(x = outcome) +
  geom_density()

COMPOSITION

Pension Surplus

ggplot(pension_surplus) +
  aes(x = item, y = balance, fill = balance > 0) +
  geom_col() +
  theme(axis.text.x = element_text(angle = 90, hjust = 1)) + 
  coord_flip() 

Pension Liabilities

ggplot(pension_liabilities) +
  aes(x = year, y = liability_millions, fill = liability_type) +
  geom_col() + 
  scale_fill_colorblind()

Homework part 1

library(ggplot2)
library(CodeClanData)
library(dplyr)

1. Take the data in the dataset qb_revenue_breakdown and make a stacked bar chart showing the sources of revenue across the two years in the dataset.

ggplot(qb_revenue_breakdown) +
  aes(x = Year, y = Revenue, fill = Product) +
  geom_col()

2. Make a line chart showing monthly sales of the “flagship product” - the KwikBit Unit1 - over the last year. This data is inside qb_monthly_sales, but you will need to use subset.

kwikbit_sales <- subset(qb_monthly_sales, Cashflow == "Kwikbit Unit 1 Sales")

ggplot(kwikbit_sales) +
  aes(x = Date, y = Amount) +
  geom_line() 

3. Make a line chart showing monthly revenue and costs over the last year. This data is also in qb_monthly_sales.

revenue_and_costs <- subset(qb_monthly_sales, Cashflow != "Kwikbit Unit 1 Sales")

ggplot(revenue_and_costs) +
  aes(x = Date, y = Amount, colour = Cashflow) +
  geom_line()

4. Show annual sales of personal fitness trackers over the last 5 years broken down by company as a ribbon plot (use geom_area). This data is in qb_competitors.

ggplot(qb_competitors) +
  aes(x = Year, y = Revenue, fill = Company) +
  geom_area() 

5. Now show the sales from the 5 competitors as a line graph. Include an extra layer that shows the data points used to make the lines.

ggplot(qb_competitors) +
  aes(x = Year, y = Revenue, colour = Company) +
  geom_line() +
  geom_point()

6. Now the company wants to compare the number of steps that their device counts vs. their competitors. Make a line graph of the number of steps throughout time, and use faceting to compare between individuals and people. Data is in qb_device_data.

qb_device_data <- 
mutate(qb_device_data, decimal_hour = hours + (mins/60))

ggplot(qb_device_data) +
  aes(x = decimal_hour, y = counts) +
  geom_line() + 
  facet_grid(id ~ device)

Take the plots that you produced in part one and now polish them by:

Adding appropriate labels Changing the scales and coordinates when appropriate. Applying a unified theme, which is described below: Graphs should have white backgrounds, and use colour sparingly. There should be faint grid lines. Font sizes should be ~12pt although titles should be slightly larger and axis labels can be slightly smaller. All plots should use colours from the following company colour scheme.

col_scheme <- c("#E89FE9", "#50434F", "#B6A7B5", "#F9A472", "#BD7040")
theme_qb <- 
  theme(
    text = element_text(size = 12),
    title = element_text(size = 14),
    axis.text = element_text(size = 10),
    panel.background = element_rect(fill = "white"),
    panel.grid = element_line(colour = "grey90", linetype = "dashed")
  )
ggplot(qb_revenue_breakdown) +
  aes(x = Year, y = Revenue, fill = Product) +
  geom_col() +
  scale_fill_manual(values = col_scheme) +
  ggtitle(
    "Breakdown of QikBit Revenue by Product Line",
    subtitle =  "2018 and 2019"
  ) +
  theme_qb

kwikbit_sales <- subset(qb_monthly_sales, Cashflow == "Kwikbit Unit 1 Sales")

ggplot(kwikbit_sales) +
  aes(x = Date, y = Amount, group = Cashflow) +
  geom_line(size = 2, colour = col_scheme[3]) +
  theme_qb +
  scale_y_continuous("Sales", labels = scales::dollar_format(prefix = "£")) +
  ggtitle("Sales of Kwikbit Unit1", subtitle = "1 Aug 2018 to 1 July 2019")

revenue_and_costs <- subset(qb_monthly_sales, Cashflow != "Kwikbit Unit 1 Sales")

ggplot(revenue_and_costs) +
  aes(x = Date, y = Amount, colour = Cashflow, group = Cashflow) +
  geom_line(size = 2) +
  theme_qb +
  scale_colour_manual(values = col_scheme) +
  scale_y_continuous("Sales", labels = scales::dollar_format(prefix = "£")) +
  ggtitle("QikBit - Revenue and Costs", subtitle = "1 Aug 2018 to 1 July 2019")

ggplot(qb_competitors) +
  aes(x = Year, y = Revenue, fill = Company) +
  geom_area() +
  scale_y_continuous(labels = scales::dollar) +
  theme_qb +
  scale_fill_manual(values = col_scheme) +
  ggtitle(
    "Revenue in the Fitness Tracker Market by Company",
    subtitle = "2015 - 2019"
  )

ggplot(qb_competitors) +
  aes(x = Year, y = Revenue, colour = Company) +
  geom_line() +
  geom_point() +
  scale_y_continuous(labels = scales::dollar) +
  theme_qb +
  scale_colour_manual(values = col_scheme) +
  ggtitle(
    "Revenue in the Fitness Tracker Market by Company",
    subtitle = "2015 - 2019"
  )

ggplot(qb_device_data) +
  aes(x = decimal_hour, y = counts, colour = device) +
  geom_line() + 
  scale_x_continuous("Time (hours)") +
  scale_y_continuous("Steps") +
  facet_grid(id ~ device) +
  scale_colour_manual(values = col_scheme) +
  theme_qb +
  ggtitle("Comparison between KwikBit Unit1 and Competitors for 5 individuals")